#!/usr/bin/env python3 import sys print("▶▶▶ START Querverweise.py", file=sys.stderr) import fitz # PyMuPDF print(" ✔ fitz importiert", file=sys.stderr) import re import tkinter as tk from tkinter import filedialog, messagebox, ttk import threading print(" ✔ tkinter importiert", file=sys.stderr) # Globale Einstellungen current_language = "de" # Standard: Deutsch create_logfile = False # Standard: Logfile aus # Übersetzungstexte texts = { "de": { "window_title": "QElectroTech - Querverweis-Analyse", "pdf_select": "PDF-Datei auswählen:", "browse": "Durchsuchen", "scan_tab": "Querverweise scannen", "settings_tab": "Einstellungen", "format_label": "Querverweis-Format:", "x_x": "X.X", "x_x_x": "X.X.X", "scan_start": "Scan starten", "exit": "Beenden", "pdf_success": "PDF {filepath} erfolgreich geöffnet. Seiten: {pages}", "log_pdf_selected": "PDF-Datei ausgewählt: {filepath}", "error_no_pdf": "Bitte PDF-Datei angeben.", "error": "Fehler", "success_pdf_saved": "PDF mit Verlinkung gespeichert: {save_pdf_path}", "success_results_saved": "Ergebnisse gespeichert: {save_txt_path}", "success": "Erfolg", "pdf_scan_saved": "PDF und Scan-Ergebnisse gespeichert!", "found_refs": "Gefundene Querverweise: {count}", "log_link": "Link: {ref} auf Seite {page} → Zielseite {target_page}", "error_creating_link": "Fehler beim Erstellen des Links für {ref} auf Seite {page}: {error}", "error_extraction": "Fehler beim Extrahieren des Zielwerts aus {ref}: {error}", "language": "Sprache", "logfile": "Logfile erstellen?", "yes": "Ja", "no": "Nein" }, "en": { "window_title": "QElectroTech - Cross-Reference Analysis", "pdf_select": "Select PDF File:", "browse": "Browse", "scan_tab": "Scan Cross-References", "settings_tab": "Settings", "format_label": "Reference Format:", "x_x": "X.X", "x_x_x": "X.X.X", "scan_start": "Start Scan", "exit": "Exit", "pdf_success": "PDF {filepath} opened successfully. Pages: {pages}", "log_pdf_selected": "PDF file selected: {filepath}", "error_no_pdf": "Please specify a PDF file.", "error": "Error", "success_pdf_saved": "PDF with links saved: {save_pdf_path}", "success_results_saved": "Results saved: {save_txt_path}", "success": "Success", "pdf_scan_saved": "PDF and scan results saved!", "found_refs": "Found cross-references: {count}", "log_link": "Link: {ref} on page {page} → Target page {target_page}", "error_creating_link": "Error creating link for {ref} on page {page}: {error}", "error_extraction": "Error extracting target from {ref}: {error}", "language": "Language", "logfile": "Create logfile?", "yes": "Yes", "no": "No" } } # Neue globale Variablen für Skip-Range skip_enabled = False skip_from = None skip_to = None # Regex zum Extrahieren der Seitenzahl im PDF page_num_pattern = re.compile(r"Seite[:\s]*(\d{1,3})", re.IGNORECASE) # ------------------------------ # Funktionen # ------------------------------ def log_message(message): text_log.insert(tk.END, message + "\n") text_log.yview(tk.END) print(message, file=sys.stderr) def is_date(candidate): return re.fullmatch(r"(0?[1-9]|[12]\d|3[01])\.(0?[1-9]|1[0-2])\.(\d{2}|\d{4})", candidate) is not None def extract_page_mapping(doc): """ Durchsucht jede Seite im PDF nach dem Text 'Seite: X' in der unteren Ecke und erstellt ein Mapping {plan_seite: pdf_page_index}. """ mapping = {} for idx in range(len(doc)): page = doc.load_page(idx) text = page.get_text("text") match = page_num_pattern.search(text) if match: plan_num = int(match.group(1)) mapping[plan_num] = idx return mapping def scan_and_link_pdf(): global skip_from, skip_to # Skip-Range auslesen skip = var_skip.get() if skip: try: sf = int(entry_from.get()) st = int(entry_to.get()) if sf < 1 or st < sf: raise ValueError("Bereich ungültig") skip_from, skip_to = sf, st except Exception as e: messagebox.showerror(texts[current_language]["error"], f"Ungültiger Seitenbereich: {e}") return else: skip_from = skip_to = None pdf_path = entry_pdf_path.get() ref_pattern = r"\b\d{1,3}\.\d{1,3}(?:\.\d{1,3})?\b" if not pdf_path: messagebox.showerror(texts[current_language]["error"], texts[current_language]["error_no_pdf"]) log_message(texts[current_language]["error_no_pdf"]) return try: doc = fitz.open(pdf_path) total_pages = len(doc) log_message(texts[current_language]["pdf_success"].format(filepath=pdf_path, pages=total_pages)) # 1. Mapping extrahieren page_mapping = extract_page_mapping(doc) if not page_mapping: log_message("Warnung: Keine Seitenzahlen im PDF gefunden. Mapping unvollständig.") results = [] # 2. Querverweise suchen und verlinken for page_num in range(total_pages): if skip and skip_from <= page_num+1 <= skip_to: continue page = doc.load_page(page_num) text_dict = page.get_text("dict") for block in text_dict.get("blocks", []): if block.get("type") != 0: continue for line in block.get("lines", []): for span in line.get("spans", []): span_text = span.get("text", "") for match in re.finditer(ref_pattern, span_text): ref_full = match.group(0).strip() if is_date(ref_full): continue results.append((ref_full, page_num + 1)) try: plan_page = int(ref_full.split('.')[0]) target_idx = page_mapping[plan_page] except Exception as ex: log_message(texts[current_language]["error_extraction"].format(ref=ref_full, error=ex)) continue try: rect = fitz.Rect(span["bbox"]) page.insert_link({"kind": fitz.LINK_GOTO, "page": target_idx, "from": rect}) log_message(texts[current_language]["log_link"].format(ref=ref_full, page=page_num+1, target_page=target_idx+1)) except Exception as e: log_message(texts[current_language]["error_creating_link"].format(ref=ref_full, page=page_num+1, error=e)) log_message(texts[current_language]["found_refs"].format(count=len(results))) # Logfile erstellen if create_logfile: save_txt_path = filedialog.asksaveasfilename(defaultextension=".txt", filetypes=[("Text Files", "*.txt")]) if save_txt_path: with open(save_txt_path, "w", encoding="utf-8") as file: for ref, page in results: file.write(f"Querverweis {ref} auf Seite {page}\n") log_message(texts[current_language]["success_results_saved"].format(save_txt_path=save_txt_path)) # PDF speichern save_pdf_path = filedialog.asksaveasfilename(defaultextension=".pdf", filetypes=[("PDF Files", "*.pdf")]) if save_pdf_path: doc.save(save_pdf_path) log_message(texts[current_language]["success_pdf_saved"].format(save_pdf_path=save_pdf_path)) messagebox.showinfo(texts[current_language]["success"], texts[current_language]["pdf_scan_saved"]) except Exception as e: messagebox.showerror(texts[current_language]["error"], f"{texts[current_language]['error']}: {e}") log_message(f"{texts[current_language]['error']}: {e}") # ------------------------------ # GUI-Aufbau # ------------------------------ root = tk.Tk() root.title(texts[current_language]["window_title"]) root.geometry("800x600") # Oberer Bereich: PDF-Auswahl frame_top = tk.Frame(root) frame_top.pack(pady=5, fill=tk.X) label_pdf_select = tk.Label(frame_top, text=texts[current_language]["pdf_select"]) label_pdf_select.pack(side=tk.LEFT, padx=5) entry_pdf_path = tk.Entry(frame_top, width=50) entry_pdf_path.pack(side=tk.LEFT, padx=5) button_browse = tk.Button(frame_top, text=texts[current_language]["browse"], command=lambda: setattr(entry_pdf_path, 'text', '') or entry_pdf_path.delete(0, tk.END) or filedialog.askopenfilename(filetypes=[("PDF Files", "*.pdf")]) or None) button_browse.config(command=lambda: (entry_pdf_path.delete(0, tk.END), entry_pdf_path.insert(0, filedialog.askopenfilename(filetypes=[("PDF Files", "*.pdf")])), log_message(texts[current_language]["log_pdf_selected"].format(filepath=entry_pdf_path.get())))) button_browse.pack(side=tk.LEFT, padx=5) # Notebook (Tabs) tab_control = ttk.Notebook(root) # Tab 1: Querverweise scannen frame_scan = ttk.Frame(tab_control) tab_control.add(frame_scan, text=texts[current_language]["scan_tab"]) frame_skip = tk.Frame(frame_scan) frame_skip.pack(pady=5, fill=tk.X) var_skip = tk.BooleanVar(value=False) chk_skip = tk.Checkbutton(frame_skip, text="Seiten überspringen", variable=var_skip, command=lambda: (entry_from.config(state="normal" if var_skip.get() else "disabled"), entry_to.config(state="normal" if var_skip.get() else "disabled"))) chk_skip.pack(side=tk.LEFT, padx=5) label_from = tk.Label(frame_skip, text="von:") label_from.pack(side=tk.LEFT, padx=(20,2)) entry_from = tk.Entry(frame_skip, width=5, state="disabled") entry_from.pack(side=tk.LEFT) label_to = tk.Label(frame_skip, text="bis:") label_to.pack(side=tk.LEFT, padx=(10,2)) entry_to = tk.Entry(frame_skip, width=5, state="disabled") entry_to.pack(side=tk.LEFT) frame_format = tk.Frame(frame_scan) frame_format.pack(pady=5) label_format = tk.Label(frame_format, text=texts[current_language]["format_label"]) label_format.pack(side=tk.LEFT, padx=5) format_var = tk.StringVar(value="X.X") radiobutton_xx = tk.Radiobutton(frame_format, text=texts[current_language]["x_x"], variable=format_var, value="X.X") radiobutton_xx.pack(side=tk.LEFT) radiobutton_xxx = tk.Radiobutton(frame_format, text=texts[current_language]["x_x_x"], variable=format_var, value="X.X.X") radiobutton_xxx.pack(side=tk.LEFT) button_scan = tk.Button(frame_scan, text=texts[current_language]["scan_start"], command=lambda: threading.Thread(target=scan_and_link_pdf, daemon=True).start()) button_scan.pack(pady=5) text_log = tk.Text(frame_scan, wrap=tk.WORD, height=20) text_log.pack(expand=True, fill=tk.BOTH, padx=10, pady=10) # Tab 2: Einstellungen frame_settings = ttk.Frame(tab_control) tab_control.add(frame_settings, text=texts[current_language]["settings_tab"]) label_language = tk.Label(frame_settings, text=texts[current_language]["language"]) label_language.pack(pady=5) combo_language = ttk.Combobox(frame_settings, values=["Deutsch", "English"], state="readonly") combo_language.current(0) combo_language.bind("<>", lambda e: None) combo_language.pack(pady=5) label_logfile = tk.Label(frame_settings, text=texts[current_language]["logfile"]) label_logfile.pack(pady=5) combo_logfile = ttk.Combobox(frame_settings, values=(texts[current_language]["yes"], texts[current_language]["no"]), state="readonly") combo_logfile.current(1) combo_logfile.bind("<>", lambda e: None) combo_logfile.pack(pady=5) tab_control.pack(expand=True, fill=tk.BOTH) button_exit = tk.Button(root, text=texts[current_language]["exit"], command=root.destroy) button_exit.pack(pady=5) print(" ✔ Vor root.mainloop()", file=sys.stderr) root.mainloop() print(" ✔ Nach root.mainloop() - Programm beendet", file=sys.stderr)